1 files changed, 110 insertions, 81 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1111d9d08903..c37a89eda90f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -38,6 +38,7 @@
 #include <asm/desc.h>
 #include <asm/fpu/api.h>
 #include <asm/fpu/xstate.h>
+#include <asm/fred.h>
 #include <asm/idtentry.h>
 #include <asm/io.h>
 #include <asm/irq_remapping.h>
@@ -49,6 +50,8 @@
 #include <asm/spec-ctrl.h>
 #include <asm/vmx.h>
 
+#include <trace/events/ipi.h>
+
 #include "capabilities.h"
 #include "cpuid.h"
 #include "hyperv.h"
@@ -159,7 +162,7 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO);
 
 /*
  * List of MSRs that can be directly passed to the guest.
- * In addition to these x2apic and PT MSRs are handled specially.
+ * In addition to these x2apic, PT and LBR MSRs are handled specially.
  */
 static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = {
 	MSR_IA32_SPEC_CTRL,
@@ -388,7 +391,16 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
 
 static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
 {
-	vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
+	/*
+	 * Disable VERW's behavior of clearing CPU buffers for the guest if the
+	 * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled
+	 * the mitigation. Disabling the clearing behavior provides a
+	 * performance boost for guests that aren't aware that manually clearing
+	 * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry
+	 * and VM-Exit.
+	 */
+	vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) &&
+				(host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) &&
 				!boot_cpu_has_bug(X86_BUG_MDS) &&
 				!boot_cpu_has_bug(X86_BUG_TAA);
 
@@ -658,25 +670,14 @@ static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu)
 	return flexpriority_enabled && lapic_in_kernel(vcpu);
 }
 
-static int possible_passthrough_msr_slot(u32 msr)
-{
-	u32 i;
-
-	for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++)
-		if (vmx_possible_passthrough_msrs[i] == msr)
-			return i;
-
-	return -ENOENT;
-}
-
-static bool is_valid_passthrough_msr(u32 msr)
+static int vmx_get_passthrough_msr_slot(u32 msr)
 {
-	bool r;
+	int i;
 
 	switch (msr) {
 	case 0x800 ... 0x8ff:
 		/* x2APIC MSRs. These are handled in vmx_update_msr_bitmap_x2apic() */
-		return true;
+		return -ENOENT;
 	case MSR_IA32_RTIT_STATUS:
 	case MSR_IA32_RTIT_OUTPUT_BASE:
 	case MSR_IA32_RTIT_OUTPUT_MASK:
@@ -691,14 +692,16 @@ static bool is_valid_passthrough_msr(u32 msr)
 	case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8:
 	case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8:
 		/* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */
-		return true;
+		return -ENOENT;
 	}
 
-	r = possible_passthrough_msr_slot(msr) != -ENOENT;
-
-	WARN(!r, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr);
+	for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) {
+		if (vmx_possible_passthrough_msrs[i] == msr)
+			return i;
+	}
 
-	return r;
+	WARN(1, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr);
+	return -ENOENT;
 }
 
 struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr)
@@ -1281,8 +1284,6 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	u16 fs_sel, gs_sel;
 	int i;
 
-	vmx->req_immediate_exit = false;
-
 	/*
 	 * Note that guest MSRs to be saved/restored can also be changed
 	 * when guest state is loaded. This happens when guest transitions
@@ -3954,6 +3955,7 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+	int idx;
 
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
@@ -3963,16 +3965,13 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
 	/*
 	 * Mark the desired intercept state in shadow bitmap, this is needed
 	 * for resync when the MSR filters change.
-	*/
-	if (is_valid_passthrough_msr(msr)) {
-		int idx = possible_passthrough_msr_slot(msr);
-
-		if (idx != -ENOENT) {
-			if (type & MSR_TYPE_R)
-				clear_bit(idx, vmx->shadow_msr_intercept.read);
-			if (type & MSR_TYPE_W)
-				clear_bit(idx, vmx->shadow_msr_intercept.write);
-		}
+	 */
+	idx = vmx_get_passthrough_msr_slot(msr);
+	if (idx >= 0) {
+		if (type & MSR_TYPE_R)
+			clear_bit(idx, vmx->shadow_msr_intercept.read);
+		if (type & MSR_TYPE_W)
+			clear_bit(idx, vmx->shadow_msr_intercept.write);
 	}
 
 	if ((type & MSR_TYPE_R) &&
@@ -3998,6 +3997,7 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+	int idx;
 
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
@@ -4007,16 +4007,13 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
 	/*
 	 * Mark the desired intercept state in shadow bitmap, this is needed
 	 * for resync when the MSR filter changes.
-	*/
-	if (is_valid_passthrough_msr(msr)) {
-		int idx = possible_passthrough_msr_slot(msr);
-
-		if (idx != -ENOENT) {
-			if (type & MSR_TYPE_R)
-				set_bit(idx, vmx->shadow_msr_intercept.read);
-			if (type & MSR_TYPE_W)
-				set_bit(idx, vmx->shadow_msr_intercept.write);
-		}
+	 */
+	idx = vmx_get_passthrough_msr_slot(msr);
+	if (idx >= 0) {
+		if (type & MSR_TYPE_R)
+			set_bit(idx, vmx->shadow_msr_intercept.read);
+		if (type & MSR_TYPE_W)
+			set_bit(idx, vmx->shadow_msr_intercept.write);
 	}
 
 	if (type & MSR_TYPE_R)
@@ -4127,6 +4124,9 @@ static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 i;
 
+	if (!cpu_has_vmx_msr_bitmap())
+		return;
+
 	/*
 	 * Redo intercept permissions for MSRs that KVM is passing through to
 	 * the guest.  Disabling interception will check the new MSR filter and
@@ -5566,10 +5566,7 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 
 	reg = DEBUG_REG_ACCESS_REG(exit_qualification);
 	if (exit_qualification & TYPE_MOV_FROM_DR) {
-		unsigned long val;
-
-		kvm_get_dr(vcpu, dr, &val);
-		kvm_register_write(vcpu, reg, val);
+		kvm_register_write(vcpu, reg, kvm_get_dr(vcpu, dr));
 		err = 0;
 	} else {
 		err = kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg));
@@ -5991,22 +5988,46 @@ static int handle_pml_full(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu)
+static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu,
+						   bool force_immediate_exit)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (!vmx->req_immediate_exit &&
-	    !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) {
-		kvm_lapic_expired_hv_timer(vcpu);
+	/*
+	 * In the *extremely* unlikely scenario that this is a spurious VM-Exit
+	 * due to the timer expiring while it was "soft" disabled, just eat the
+	 * exit and re-enter the guest.
+	 */
+	if (unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled))
 		return EXIT_FASTPATH_REENTER_GUEST;
-	}
 
-	return EXIT_FASTPATH_NONE;
+	/*
+	 * If the timer expired because KVM used it to force an immediate exit,
+	 * then mission accomplished.
+	 */
+	if (force_immediate_exit)
+		return EXIT_FASTPATH_EXIT_HANDLED;
+
+	/*
+	 * If L2 is active, go down the slow path as emulating the guest timer
+	 * expiration likely requires synthesizing a nested VM-Exit.
+	 */
+	if (is_guest_mode(vcpu))
+		return EXIT_FASTPATH_NONE;
+
+	kvm_lapic_expired_hv_timer(vcpu);
+	return EXIT_FASTPATH_REENTER_GUEST;
 }
 
 static int handle_preemption_timer(struct kvm_vcpu *vcpu)
 {
-	handle_fastpath_preemption_timer(vcpu);
+	/*
+	 * This non-fastpath handler is reached if and only if the preemption
+	 * timer was being used to emulate a guest timer while L2 is active.
+	 * All other scenarios are supposed to be handled in the fastpath.
+	 */
+	WARN_ON_ONCE(!is_guest_mode(vcpu));
+	kvm_lapic_expired_hv_timer(vcpu);
 	return 1;
 }
 
@@ -6509,7 +6530,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
 		vcpu->run->internal.data[0] = vectoring_info;
 		vcpu->run->internal.data[1] = exit_reason.full;
-		vcpu->run->internal.data[2] = vcpu->arch.exit_qualification;
+		vcpu->run->internal.data[2] = vmx_get_exit_qual(vcpu);
 		if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) {
 			vcpu->run->internal.data[ndata++] =
 				vmcs_read64(GUEST_PHYSICAL_ADDRESS);
@@ -6543,7 +6564,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 
 	if (exit_reason.basic >= kvm_vmx_max_exit_handlers)
 		goto unexpected_vmexit;
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	if (exit_reason.basic == EXIT_REASON_MSR_WRITE)
 		return kvm_emulate_wrmsr(vcpu);
 	else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER)
@@ -6960,14 +6981,16 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 {
 	u32 intr_info = vmx_get_intr_info(vcpu);
 	unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK;
-	gate_desc *desc = (gate_desc *)host_idt_base + vector;
 
 	if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm,
 	    "unexpected VM-Exit interrupt info: 0x%x", intr_info))
 		return;
 
 	kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ);
-	vmx_do_interrupt_irqoff(gate_offset(desc));
+	if (cpu_feature_enabled(X86_FEATURE_FRED))
+		fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector);
+	else
+		vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector));
 	kvm_after_interrupt(vcpu);
 
 	vcpu->arch.at_instruction_boundary = true;
@@ -7146,13 +7169,13 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host, false);
 }
 
-static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
+static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u64 tscl;
 	u32 delta_tsc;
 
-	if (vmx->req_immediate_exit) {
+	if (force_immediate_exit) {
 		vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0);
 		vmx->loaded_vmcs->hv_timer_soft_disabled = false;
 	} else if (vmx->hv_deadline_tsc != -1) {
@@ -7205,13 +7228,22 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,
 	barrier_nospec();
 }
 
-static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
+static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu,
+					     bool force_immediate_exit)
 {
+	/*
+	 * If L2 is active, some VMX preemption timer exits can be handled in
+	 * the fastpath even, all other exits must use the slow path.
+	 */
+	if (is_guest_mode(vcpu) &&
+	    to_vmx(vcpu)->exit_reason.basic != EXIT_REASON_PREEMPTION_TIMER)
+		return EXIT_FASTPATH_NONE;
+
 	switch (to_vmx(vcpu)->exit_reason.basic) {
 	case EXIT_REASON_MSR_WRITE:
 		return handle_fastpath_set_msr_irqoff(vcpu);
 	case EXIT_REASON_PREEMPTION_TIMER:
-		return handle_fastpath_preemption_timer(vcpu);
+		return handle_fastpath_preemption_timer(vcpu, force_immediate_exit);
 	default:
 		return EXIT_FASTPATH_NONE;
 	}
@@ -7224,11 +7256,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 
 	guest_state_enter_irqoff();
 
-	/* L1D Flush includes CPU buffer clear to mitigate MDS */
+	/*
+	 * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW
+	 * mitigation for MDS is done late in VMentry and is still
+	 * executed in spite of L1D Flush. This is because an extra VERW
+	 * should not matter much after the big hammer L1D Flush.
+	 */
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
 		vmx_l1d_flush(vcpu);
-	else if (static_branch_unlikely(&mds_user_clear))
-		mds_clear_cpu_buffers();
 	else if (static_branch_unlikely(&mmio_stale_data_clear) &&
 		 kvm_arch_has_assigned_device(vcpu->kvm))
 		mds_clear_cpu_buffers();
@@ -7260,7 +7295,10 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 	if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI &&
 	    is_nmi(vmx_get_intr_info(vcpu))) {
 		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
-		vmx_do_nmi_irqoff();
+		if (cpu_feature_enabled(X86_FEATURE_FRED))
+			fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR);
+		else
+			vmx_do_nmi_irqoff();
 		kvm_after_interrupt(vcpu);
 	}
 
@@ -7268,7 +7306,7 @@ out:
 	guest_state_exit_irqoff();
 }
 
-static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
+static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long cr3, cr4;
@@ -7295,7 +7333,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		return EXIT_FASTPATH_NONE;
 	}
 
-	trace_kvm_entry(vcpu);
+	trace_kvm_entry(vcpu, force_immediate_exit);
 
 	if (vmx->ple_window_dirty) {
 		vmx->ple_window_dirty = false;
@@ -7354,7 +7392,9 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmx_passthrough_lbr_msrs(vcpu);
 
 	if (enable_preemption_timer)
-		vmx_update_hv_timer(vcpu);
+		vmx_update_hv_timer(vcpu, force_immediate_exit);
+	else if (force_immediate_exit)
+		smp_send_reschedule(vcpu->cpu);
 
 	kvm_wait_lapic_expire(vcpu);
 
@@ -7418,10 +7458,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	vmx_recover_nmi_blocking(vmx);
 	vmx_complete_interrupts(vmx);
 
-	if (is_guest_mode(vcpu))
-		return EXIT_FASTPATH_NONE;
-
-	return vmx_exit_handlers_fastpath(vcpu);
+	return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit);
 }
 
 static void vmx_vcpu_free(struct kvm_vcpu *vcpu)
@@ -7901,11 +7938,6 @@ static __init void vmx_set_cpu_caps(void)
 		kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG);
 }
 
-static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
-{
-	to_vmx(vcpu)->req_immediate_exit = true;
-}
-
 static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
 				  struct x86_instruction_info *info)
 {
@@ -8358,8 +8390,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.check_intercept = vmx_check_intercept,
 	.handle_exit_irqoff = vmx_handle_exit_irqoff,
 
-	.request_immediate_exit = vmx_request_immediate_exit,
-
 	.sched_in = vmx_sched_in,
 
 	.cpu_dirty_log_size = PML_ENTITY_NUM,
@@ -8619,7 +8649,6 @@ static __init int hardware_setup(void)
 	if (!enable_preemption_timer) {
 		vmx_x86_ops.set_hv_timer = NULL;
 		vmx_x86_ops.cancel_hv_timer = NULL;
-		vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit;
 	}
 
 	kvm_caps.supported_mce_cap |= MCG_LMCE_P;